.png){kind=icon}
.png){kind=icon}
Return
Visual tracking via robust multi-task multi-feature joint sparse representation
.png){kind=icon}
PRE
AI
DOI：10.1007/s11042-018-6198-8.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Multiple feature object representation has been proved as a robust approach for visual tracking. Different types of situations such as occlusion, rotation and illumination may occur during tracking, especially long sequences. Robust tracking could be obtained as multiple features could complement each other. In this paper, we cast visual tracking as a novel multi-task sparse learning problem and exploit various types of visual features, such as intensity, color, texture and edge, where each feature can be sparsely represented by a linear combination of atoms from an adaptive feature template. We use an on-line feature selection mechanism based on the two-class variance ratio measure, applied to log likelihood distributions computed with respect to a given feature from samples of object and background pixels. The proposed method is integrated in a particle filtering framework. We jointly consider the underlying relationship across different particles, and tackle it in a unified robust multi-task formulation. In addition, to capture the frequently emerging outlier tasks, we make fully use of a decomposition model which enables a more robust and accurate approximation. We show that the proposed model can be efficiently solved using the Alternating direction method of multipliers (ADMM) with a small number of closed-form updates. Four types of features are implemented and tested on numerous benchmark video sequences. Both the qualitative and quantitative results demonstrate the superior performance of the proposed approach compared to 9 state of-the-art trackers.
Keywords:
Feature selection
Multi-task sparse learning
Decomposition model
Alternating direction method of multipliers
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3
Papers:
1.9W
Citations:
3.2W